olympe
genetic-programming
| olympe | genetic-programming | |
|---|---|---|
| 1 | 1 | |
| 5 | 5 | |
| - | - | |
| 10.0 | 10.0 | |
| over 1 year ago | over 8 years ago | |
| TypeScript | Common Lisp | |
| - | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
olympe
-
Replacing a SQL analyst with 26 recursive GPT prompts
It only support Postgres for now (and it's far from perfect..)
https://github.com/BenderV/olympe
genetic-programming
-
Replacing a SQL analyst with 26 recursive GPT prompts
A couple of thoughts jumped out after reading this: transforms and meta-learning.
An old trick in AI is to transform the medium to Lisp because it can be represented as a syntax-free tree that always runs. In this case, working with SQL directly led to syntax errors which returned no results. It would probably be more fruitful to work with relational algebra and tuple relational calculus (I had to look that up hah) represented as Lisp and convert the final answer back to SQL. But I'm honestly impressed that ChatGPT's SQL answers mostly worked anyway!
https://en.wikipedia.org/wiki/Genetic_programming
http://www.cis.umassd.edu/~ivalova/Spring08/cis412/Ectures/G...
https://www.gene-expression-programming.com/GepBook/Chapter1...
https://github.com/gdobbins/genetic-programming
I actually don't know how far things have come with meta-learning as far as AIs tuning their own hyperparameters. Well, a quick google search turned up this:
https://cloud.google.com/ai-platform/training/docs/hyperpara...
So I would guess that this is the secret sauce that's boosted AI to such better performance in the last year or two. It's always been obvious to do that, but it requires a certain level of computing power to be able to run trainings thousands of times to pick the best learners.
Anyway, my point is that the author is doing the above steps semi-manually, but AIs are beginning to self-manage. Recursion sounds like a handy term to convey that. ChatGPT is so complex compared to what he is doing that I don't see any reason why it couldn't take his place too! And with so many eyeballs on this stuff, we probably only have a year or two before AI can do it all.
I'm regurgitating 20 year old knowledge here as an armchair warrior. Insiders are so far beyond this. But see, everything I mentioned is so much easier to understand than neural networks, that there's no reason why NNs can't use these techniques themselves. The hard work has already been done, now it's just plug n chug.
What are some alternatives?
lambdaprompt - λprompt - A functional programming interface for building AI systems
zillion - Make sense of it all. Semantic data modeling and analytics with a sprinkle of AI. https://totalhack.github.io/zillion/
tellery - Tellery lets you build metrics using SQL and bring them to your team. As easy as using a document. As powerful as a data modeling tool.
vulcan-sql - Data API Framework for AI Agents and Data Apps
sketch - AI code-writing assistant that understands data content